🕵️‍♂️ Code Broker: Multi-Agent Code Assessment System

Code Broker is a sophisticated multi-agent system powered by Google's Agent Development Kit (ADK) and Gemini models. It employs a team of specialized AI agents to analyze your code, assess its quality, and generate comprehensive HTML reports.

✨ Features

• 🔍 Code Description: Analyzes structure, architecture, and logic.
• ✅ Correctness Assessment: Evaluates functionality, security, efficiency, and error handling.
• 🎨 Style Assessment: Checks readability, maintainability, linting scores, and best practices.
• 💡 Improvement Recommendations: Provides actionable suggestions to enhance your codebase.
• 📊 Comprehensive Reporting: Generates a beautiful interactive HTML report with all findings.

---

🚀 Installation

📦 From PyPI (Coming Soon)

pip install code-broker

🛠️ From Source (Development)

If you want to run the latest version or contribute:

1. Clone the repository:

   git clone https://github.com/Samir-atra/Code_broker_pkg.git
   cd code_broker

2. Create a Virtual Environment (Recommended):

   python3 -m venv .venv
   source .venv/bin/activate

3. Install in Editable Mode:

   pip install -e .

---

⚙️ Configuration

Before running Code Broker, you need to configure your API keys.

1. Create a .env file in your project root or the directory where you run the tool:

   touch .env

2. Add your credentials: Open .env and add the following:

   # Required: Your Google Gemini API Key
   GOOGLE_API_KEY=your_gemini_api_key_here
   
   # Optional: For analyzing private GitHub repositories
   GITHUB_TOKEN=your_github_personal_access_token

   🔑 Get your Google API Key here: Google AI Studio

---

🏃‍♂️ Usage

Once installed, you can use the code-broker CLI command to analyze files, directories, or repositories.

📝 Analyze a Local File

code-broker /path/to/your/script.py

📂 Analyze a Directory

code-broker /path/to/your/project/src

🌐 Analyze a GitHub Repository

code-broker https://github.com/username/repository

---

📄 Output

After analysis, Code Broker will:

1. Display a summary in your terminal.
2. Generate a detailed HTML Report in the reports/ directory.
3. Automatically open the report in your default web browser.

---

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.